snehasree-sony

Results 2 comments of snehasree-sony

As I understand from the paper for training C-ViViT - MiT dataset is used, for training phenaki what is the dataset used for text to video generation ?

I would like to know what all datasets are used for training C-ViViT and Phenaki. For C-ViViT training I understand that MiT dataset is used. I would like to know...